{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu-pro","formal_name":"MMLU-Pro","introduction":"MMLU-Pro rebuilds MMLU with ten answer options instead of four and removes items that no longer separate models. Questions span fourteen academic and professional subjects.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"c855caba-ba94-5c6c-b8fd-da82e663084a","task_key":"default--test--2083","task_revision_id":"1","upstream_id":"2083","short_description":"If adverse impact on some minority group has been observed, which of the…","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['Projective', 'Empirically keyed', 'Personality test', 'Multiple-choice', 'Computer adaptive test', 'Integrity test', 'Work sample', 'Situational judgement test', 'Cognitive ability test', 'Polygraph test']\",\"question\":\"If adverse impact on some minority group has been observed, which of the following types of tests probably has the best chance of withstanding legal challenge\",\"src\":\"ori_mmlu-professional_psychology\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}